Current advances in text-driven 3D scene editing tasks typically render the 3D representations into multi-view images and modify the images with the text instructions. Context consistency across multiple views and cross-modal consistency in the single-view are the keys to effective 3D editing. Accordingly, existing methods introduce additional image constraints and apply pre-trained 2D editing models. However, they fix the same text instruction across all views and freeze the pre-trained 2D model for single-view editing, leading to deficient modeling of 3D scene views and results in inconsistent generations with visual artifacts. To address these limitations, we introduce a discretized 3D view modeling method and a diffusion-based multi-view consistent editing pipeline for text-driven 3D gaussian splatting editing, abbreviated as D2Gaussian. Specifically, our approach constructs a codebook that encodes continuous 3D view information into discrete token embeddings to model the spatial feature expressions. Then, the token embeddings are proposed to guide and finetune the diffusion-based image editing model with the dynamic addition of control conditions, yielding a multi-view consistent editing pipeline. Finally, we introduce a 3D editing dataset generation approach along with a 3D-CLIP-SIM metric to form a benchmark, 3D-MagicBrush, to provide more diverse evaluation scenarios for future 3D editing works. Experiments demonstrate that our method achieves better visual results and multi-view consistency than previous state-of-the-art methods.
论文检索
输入标题、作者或关键词，从 1,620 篇学术成果中精准定位
Cooking process visualization is a promising task in the intersection of image generation and food analysis, which aims to generate an image for each cooking step of a recipe. However, most existing works focus on generating images of finished foods based on the given recipes, and face two challenges in visualizing the cooking process. First, the appearance of ingredients changes variously across cooking steps, it is difficult to generate the correct appearances of foods that match the textual description, leading to semantic inconsistency. Second, the current step might depend on the operations of previous step, it is crucial to maintain the contextual coherence of images in sequential order. In this work, we present a cooking process visualization model, called Chain-of-Cooking. Specifically, to generate correct appearances of ingredients, we present a Dynamic Patch Selection Module to retrieve previously generated image patches as references, which are most related to current textual contents. Furthermore, to enhance the coherence and keep the rational order of generated images, we propose a Semantic Evolution Module and a Bidirectional Chain-of-Thought (CoT) Guidance. To better utilize the semantics of previous texts, the Semantic Evolution Module establishes the semantical association between latent prompts and current cooking step, and merges it with the latent features. Then the CoT Guidance updates the merged features to guide the current cooking step remain coherent with the previous step. Moreover, we construct a dataset named CookViz, consisting of intermediate image-text pairs for the cooking process. Quantitative and qualitative experiments show that our method outperforms existing methods in generating coherent and semantic consistent cooking process.
Instruction-based image editing enables intuitive modifications of images through natural language descriptions. However, existing models often struggle to accurately identify the target region, which refers to the area that should be modified. As a result, unintended changes may occur in non-target areas, where the original image should remain unchanged. To address this issue, we propose FoRE, an MLLM-guided framework that identifies the target region based on the given edit instruction and performs image editing using region-aware embeddings. Within FoRE, the Region-guided Edit Adapter projects these embeddings from the MLLM domain to the diffusion condition space. Subsequently, the Region-guided Refinement Module refines the projected features to enhance spatial accuracy prior to guiding the diffusion process. Through comprehensive evaluations, we demonstrate that FoRE significantly improves localization accuracy and instruction fidelity compared to existing approaches. By explicitly incorporating region-aware conditioning, our framework effectively bridges the gap between instruction comprehension and spatially precise image modifications, advancing the capabilities of instruction-based image editing.
With the rapid advancement and widespread adoption of VR/AR technologies, there is a growing demand for the creation of high-quality, immersive dynamic scenes. However, existing generation works predominantly concentrate on the creation of static scenes or narrow perspective-view dynamic scenes, falling short of delivering a truly 360-degree immersive experience from any viewpoint. In this paper, we introduce TiP4GEN, an advanced text-to-dynamic panorama scene generation framework that enables fine-grained content control and synthesizes motion-rich, geometry-consistent panoramic 4D scenes. TiP4GEN integrates panorama video generation and dynamic scene reconstruction to create 360-degree immersive virtual environments. For video generation, we introduce a Dual-branch Generation Model consisting of a panorama branch and a perspective branch, responsible for global and local view generation, respectively. A bidirectional cross-attention mechanism facilitates comprehensive information exchange between the branches. For scene reconstruction, we propose a Geometry-aligned Reconstruction Model based on 3D Gaussian Splatting. By aligning spatial-temporal point clouds using metric depth maps and initializing scene cameras with estimated poses, our method ensures geometric consistency and temporal coherence for the reconstructed scenes. Extensive experiments demonstrate the effectiveness of our proposed designs and the superiority of TiP4GEN in generating visually compelling and motion-coherent dynamic panoramic scenes.
Ensuring the ethical deployment of text-to-image models requires effective techniques to prevent the generation of harmful or inappropriate content. While concept erasure methods offer a promising solution, existing finetuning-based approaches suffer from notable limitations. Anchor-free methods risk disrupting sampling trajectories, leading to visual artifacts, while anchor-based methods rely on the heuristic selection of anchor concepts. To overcome these shortcomings, we introduce a finetuning framework, dubbed ANT, which Automatically guides deNoising Trajectories to avoid unwanted concepts. ANT is built on a key insight: reversing the condition direction of classifier-free guidance during mid-to-late denoising stages enables precise content modification without sacrificing early-stage structural integrity. This inspires a trajectory-aware objective that preserves the integrity of the early-stage score function field-which steers samples toward the natural image manifold-without relying on heuristic anchor concept selection. For single-concept erasure, we propose an augmentation-enhanced weight saliency map to precisely identify the critical parameters that most significantly contribute to the unwanted concept, enabling more thorough and efficient erasure. For multi-concept erasure, our objective function offers a versatile plug-and-play solution that significantly boosts performance. Extensive experiments demonstrate that ANT achieves state-of-the-art results in both single and multi-concept erasure, delivering high-quality, safe outputs without compromising the generative fidelity. Code is available at https://github.com/lileyang1210/ANT
Recent advancements in concept customization via diffusion models have significantly enhanced controllability and quality. However, precise relation customization, which controls the position of interactions among multiple instances, remains challenging due to unpredictable initial latent noise. Existing methods primarily rely on conditional prompts and attention control, overlooking the structured potential of initial noise. This paper introduces Position-LoRA, a novel framework leveraging structural prior in initial noise to improve relation customization and layout control. Position-LoRA employs a differential fine-tuning scheme and a latent noise encoder. The guided fine-tuning enhances generation tendencies from structured initial noise, embedding explicit relationship-specific spatial information. The latent noise encoder dynamically manipulates latent noises, enabling precise spatial control and flexibility in relational image generation. Furthermore, a fine-grained guidance and control strategy is employed during generation to enhance the image-text alignment and layout alignment. Experiments demonstrate that Position-LoRA improves stability, controllability, and fidelity in relational image generation with layout control, surpassing existing concept customization and layout-to-image methods in qualitative and quantitative evaluations. Code is available at https://github.com/liyiming09/Position-LoRA.
We introduce GroupSketch, a novel method for vector sketch animation that effectively handles multi-object interactions and complex motions. Existing approaches struggle with these scenarios, either being limited to single-object cases or suffering from temporal inconsistency and poor generalization. To address these limitations, our method adopts a two-stage pipeline comprising Motion Initialization and Motion Refinement. In the first stage, the input sketch is interactively divided into semantic groups and key frames are defined, enabling the generation of a coarse animation via interpolation. In the second stage, we propose a Group-based Displacement Network (GDN), which refines the coarse animation by predicting group-specific displacement fields, leveraging priors from a text-to-video model. GDN further incorporates specialized modules, such as Context-conditioned Feature Enhancement (CCFE), to improve temporal consistency. Extensive experiments demonstrate that our approach significantly outperforms existing methods in generating high-quality, temporally consistent animations for complex, multi-object sketches, thus expanding the practical applications of sketch animation.
Motion customization aims to adapt the diffusion model (DM) to generate videos with the motion specified by a set of video clips with the same motion concept. To realize this goal, the adaptation of DM should be possible to model the specified motion concept, without compromising the ability to generate diverse appearances. Thus, the key to solving this problem lies in how to separate the motion concept from the appearance in the adaptation process of DM. Typical previous works explore different ways to represent and insert a motion concept into large-scale pre-trained text-to-video diffusion models, e.g., learning a motion LoRA, using latent noise residuals, etc. While those methods can encode the motion concept, they also inevitably encode the appearance in reference videos, resulting in weakened appearance generation capability. In this paper, we follow the typical way to learn a motion LoRA to encode the motion concept, but propose two novel strategies to enhance motion-appearance separation, including temporal attention purification (TAP) and appearance highway (AH). Specifically, we assume that in the temporal attention module, the pretrained Value embeddings are sufficient to serve as basic components needed by producing a new motion. Thus, in TAP, we choose only to reshape the temporal attention with motion LoRAs so that Value embeddings can be reorganized to produce a new motion. Further, in AH, we alter the starting point of each skip connection in U-Net from the output of each temporal attention module to the output of each spatial attention module. Extensive experiments demonstrate that compared to previous works, our method can generate videos with appearance more aligned with the text descriptions and motion more consistent with the reference videos.
As short videos become a dominant medium for news dissemination, fake news videos pose increasing threats to public trust and information integrity. Existing methods primarily focus on learning multimodal representations to predict binary veracity labels, yet they overlook the use of external evidence, which is important for identifying more sophisticated fake news that subtly exploits psychological cues and cognitive biases. Moreover, these approaches do not provide fine-grained attribution labels, which are essential for interpretable misinformation governance. To address these limitations, we introduce EvidSV, the first comprehensive benchmark supporting evidence- and attribution-aware fake news video detection. Drawing inspiration from the human cognitive process of interpreting news-related content, we propose MUKE, a multi-view knowledge progressive enhancement learning framework. By jointly analyzing both the news content and supporting evidence, MUKE (1) facilitates the understanding of news semantics to (2) progressively refine shared domain knowledge, and (3) adaptively summarizes multi-view knowledge to assess news veracity. Extensive experiments demonstrate that MUKE consistently outperforms existing methods in both fake news detection and attribution, and generalizes effectively to previously unseen domains. Our code is available at https://github.com/zzeng1998/EvidSV.
Recent advances in VR have created a growing demand for immersive content, especially in viewing music performances. However, most existing videos are captured with a narrow field of view, limiting their applicability in VR environments. In this paper, we present a practical system that converts fixed-camera music performance videos into immersive VR experiences via high-resolution video outpainting. Our method leverages pre-trained text-to-image diffusion models with multi-conditioning based on ControlNet to generate spatially and temporally consistent frames at high resolution. While our approach builds on existing components, we introduce a novel orchestration of these tools tailored specifically for immersive video generation, requiring no additional training and running efficiently on consumer GPUs. The system supports videos of arbitrary length via frame-by-frame processing and produces seamless 8K outputs through lightweight post-processing. Extensive experiments and user studies demonstrate that our system outperforms state-of-the-art methods in perceptual quality and viewer immersion, offering a scalable pathway for repurposing conventional footage into high-fidelity VR content.
Diabetic retinopathy (DR) grading plays a critical role in early clinical intervention and vision preservation. Recent explorations predominantly focus on visual lesion feature extraction through data processing and domain decoupling strategies. However, they generally overlook domain-invariant pathological patterns and underutilize the rich contextual knowledge of foundation models, relying solely on visual information, which is insufficient for distinguishing subtle pathological variations. Therefore, we propose integrating fine-grained pathological descriptions to complement prototypes with additional context, thereby resolving ambiguities in borderline cases. Specifically, we propose a Hierarchical Anchor Prototype Modulation (HAPM) framework to facilitate DR grading. First, we introduce a variance spectrum-driven anchor prototype library that preserves domain-invariant pathological patterns. We further employ a hierarchical differential prompt gating mechanism, dynamically selecting discriminative semantic prompts from both LVLM and LLM sources to address semantic confusion between adjacent DR grades. Finally, we utilize a two-stage prototype modulation strategy that progressively integrates clinical knowledge into visual prototypes through a Pathological Semantic Injector (PSI) and a Discriminative Prototype Enhancer (DPE). Extensive experiments across eight public datasets demonstrate that our approach achieves pathology-guided prototype evolution while outperforming state-of-the-art methods. The code is available at https://github.com/zhcz328/HAPM.
Mindfulness meditation has seen increasing applications in diverse domains as an effective practice to improve mental health. However, the standardized frameworks adopted by most applications often fail to cater to users with various psychological states and health conditions. This limitation arises primarily from the lack of personalization and adaptive content design. To address this, we propose MindfulVerse, an AI-Generated Content (AIGC)-driven application to create personalized and immersive mindfulness experiences. By developing a novel agent, the system can dynamically adjust the meditation content based on the ideas of individual users. Furthermore, we conducted exploratory user studies and comparative evaluations to assess the application scenarios and performance of our novel generative meditation tool in VR environments. The results of this user study indicate that generative meditation improves neural activation in self-regulation and shows a positive impact on emotional regulation and participation. Our approach offers a generative meditation procedure that provides users with an application that better suits their preferences and states.
Text-to-image person retrieval aims to identify target person images using natural language descriptions. Current state-of-the-art methods predominantly rely on single-round retrieval frameworks, where retrieval accuracy heavily depends on the quality of the initial textual descriptions. However, users sometimes struggle to provide detailed and distinctive descriptions in a single attempt, resulting in generic initial queries that lack discriminative details. This fundamental limitation of the single-round retrieval framework frequently leads to the misinterpretation of user intent and suboptimal retrieval performance. To address this limitation, we propose Dialogue-driven Interactive Dynamic Learning (DIDL) for text-to-image person retrieval. Specifically, we first introduce Collaborative Query Refinement (CQR), which progressively refines retrieval conditions through multi-round dialogues. Then, we design Dynamic Context Resampling (DCR) based on a bi-granular mask strategy that enhances the model's adaptation to dialogue-style contexts and effectively balances its attention between initial descriptions and supplementary information. Based on these components, we further propose cross-modal Probabilistic Context Matching Modeling (ProCMM) that establishes effective associations between static visual features and dynamic contextual semantics. Extensive experiments demonstrate that our approach achieves state-of-the-art performance across all three benchmark datasets.
VisAug: Facilitating Speech-Rich Web Video Navigation and Engagement with Auto-Generated Visual Augmentations
PDF ↗The widespread adoption of digital technology has ushered in a new era of digital transformation across all aspects of our lives. Online learning, social, and work activities, such as distance education, videoconferencing, interviews, and talks, have led to a dramatic increase in speech-rich video content. In contrast to other video types, such as surveillance footage, which typically contain abundant visual cues, speech-rich videos convey most of their meaningful information through the audio channel. This poses challenges for improving content consumption using existing visual-based video summarization, navigation, and exploration systems. In this paper, we present VisAug, a novel interactive system designed to enhance speech-rich video navigation and engagement by automatically generating informative and expressive visual augmentations based on the speech content of videos. Our findings suggest that this system has the potential to significantly enhance the consumption and engagement of information in an increasingly video-driven digital landscape.
Food plays a vital role in human health, and accurate nutrition estimation is crucial for guiding healthy dietary choices. Traditional biochemical-based assessment methods are often inefficient, costly, and impractical for daily use. With the continuous progress in computer vision, some vision-based nutrition estimation approaches have emerged, typically relying on RGB images alone or in combination with depth images to infer nutritional information. These methods have achieved promising performance and garnered considerable attention. However, these methods often ignore visually imperceptible ingredients such as oil, sugar, and salt, which may significantly influence the estimation of nutritional content. Besides, existing methods lack explicit mechanisms for modeling nutrient-specific information and guiding attention toward nutrition-relevant semantics. To solve the above two issues, we propose a novel ingredients-guided and nutrients-prompted nutrition estimation method. Our method adopts multi-scale feature fusion and integrates RGB and depth modalities to enhance visual representation learning. To account for invisible ingredients, we introduce an ingredients-guided strategy, which enhances the sensitivity to non-visible nutritional factors. Moreover, a nutrient-prompt mechanism is introduced to explicitly guide the focus of the model toward nutrient-relevant attributes during estimation. We validate our method on Nutrition5k, where it consistently outperforms existing state-of-the-art methods, demonstrating its efficacy.
Reversible Adversarial Example (RAE) could be used to protect the privacy and copyright of images on social networks (SONs) by exploring the adversarial examples to disrupt the access of malicious AI models while ensuring recoverability with authorized users. Existing RAE methods add adversarial perturbations in spatial images which do not apply to JPEG images, the most widely adopted image format for image storage and transmission. To tackle this issue, we propose the first Reversible Adversarial Example (JPEG-RAE) generation framework for JPEG images, which consists of two primary components, i.e., JPEG-AE and G-RDH. JPEG-AE crafts the adversarial perturbations in the JPEG domain of images by leveraging chain rule of gradient propagation, so that they could effectively mislead the AI models in spatial domain when they are JPEG decompressed. And G-RDH adopts a gradient-directed bi-directional histogram shifting scheme for efficient reversible hiding of adversarial perturbations and location data in JPEG domain, where the histogram shifting is in sync with the sign of back-propagated gradients to further boost the performance of adversarial attacks. Experimental validation demonstrates that, although confined to the JPEG format such as the amount and intensity of alterable DCT coefficients, the proposed JPEG-RAE could still show superior or comparable performance, in terms of attack ability and recover ability, to its counterparts in spatial domain.
The attention mechanism is the key to the success of transformers in different machine learning tasks. However, the quadratic complexity with respect to the sequence length of the vanilla softmax-based attention mechanism becomes the major bottleneck for the application of long sequence tasks, such as vision tasks. Although various efficient linear attention mechanisms have been proposed, they need to sacrifice performance to achieve high efficiency. What's more, memory-efficient methods, such as FlashAttention-1-3, still have quadratic computation complexity which can be further improved. In this paper, we propose a novel efficient linear fast attention (ELFATT) mechanism to achieve low memory input/output operations, linear computational complexity, and high performance at the same time. ELFATT offers 4-7x speedups over the vanilla softmax-based attention mechanism in high-resolution vision tasks without losing performance. ELFATT is FlashAttention friendly. Using FlashAttention-2 acceleration, ELFATT still offers 2-3x speedups over the vanilla softmax-based attention mechanism on high-resolution vision tasks without losing performance. Even in some non-vision tasks of long-range arena, ELFATT still achieves leading performance and offers 1.2-2.3x speedups over FlashAttention-2. Even on edge GPUs, ELFATT still offers 1.6x to 2.0x speedups compared to state-of-the-art attention mechanisms in various power modes from 5W to 60W. Furthermore, ELFATT can be used to enhance and accelerate diffusion tasks directly without training.
The rapid advancement of multimedia technologies and their increasing integration in education have underscored the importance of multimedia learning. Knowledge Tracing (KT) plays a crucial role in enabling adaptive multimedia learning by continuously monitoring students' progress and forecasting their performance throughout the learning process. Question lies at the heart of the KT process, making its representation crucial for building efficient KT models. However, the sparsity and complexity of question data pose significant challenges for existing methods to capture the underlying features of questions, thereby affecting the accuracy of knowledge state predictions. To address this issue, this paper attempts to introduce the diffusion model to the KT field, proposing a novel knowledge tracing model, DiffuQKT. The model presents a diffusion-based generative approach for question representation and enhances the stability of knowledge states through contrastive learning. Specifically, DiffuQKT first constructs question representations based on their concepts, difficulty, and variations, and then, during the forward phase, progressively adds noise to the question representations, disrupting them into a Gaussian distribution. In the reverse phase, DiffuQKT gradually recovers the representations from noise, generating higher-quality question representations for knowledge tracing. Furthermore, to guide more meaningful question generation, we incorporate question concepts and difficulty as conditions during the denoising process. In addition, to improve the robustness of knowledge states against subtle variations in question representations, we employ contrastive learning to stabilize knowledge states across both original and denoised question representations. We conduct extensive experiments on four public datasets, comparing DiffuQKT with 15 baseline methods. The results demonstrate that DiffuQKT significantly outperforms existing models. Moreover, we find that the diffusion-based generative approach for question representation proposed in this paper has the ability to significantly improve the performance of baseline models. The code can be found at https://github.com/lilstrawberry/DiffuQKT.
With the rapid evolution of multimedia technologies and its widespread integration into education, adaptive multimedia learning has gained significant prominence. Cognitive diagnosis (CD) is pivotal in this domain, as it models students' cognitive states using practice data captured by multimedia learning applications. However, existing methods often simplify these states to mere proficiency on knowledge concepts. Constructivism in education emphasizes learning as a continuous cognitive development process, during which students' cognitive states become increasingly complex, involving not only their construction of concepts but also their construction of relations between concepts that have long been overlooked. To this end, we propose the Hierarchical Disentanglement of Cognitive States for Enhanced Cognitive Diagnosis (HDCD). Inspired by the Structure of Observed Learning Outcomes (SOLO) taxonomy, which categorizes cognitive development into core hierarchical levels (Multistructural, Relational, Extended Abstract), we introduce a hierarchical disentanglement strategy to define cognitive states aligned with each SOLO level: Intra-Concept Cognitive States, Relational Cognitive States, and Extended Cognitive States. Specifically, (i) At the multistructural level, intra-concept cognitive states are sampled from student's personalized cognitive distribution, representing the construction of individual concepts. (ii) At the relational level, inter-concept cognitive states are first sampled to represent the construction of relations between concepts. We then employ a hypergraph transformation to collaboratively update both intra-concept and inter-concept cognitive states, forming relational cognitive states. Considering that students' self-constructed knowledge systems involve multiple types of inter-concept relations, relational cognitive states are implemented under both undirected and directed relation views in this work, and then fed into local diagnostic functions, respectively. (iii) At the extended abstract level, outputs from the local diagnostic functions are fused using multi-view attention mechanisms, resulting in extended cognitive states, which integrate information from multiple relational views, are then fed into a global diagnostic function for final prediction. Extensive experiments on real-world datasets demonstrate the superior performance and interpretability of our HDCD.
Understanding how scientific ideas evolve requires more than summarizing individual papers-it demands structured, cross-document reasoning over thematically related research. In this work, we formalize multi-document scientific inference, a new task that extracts and aligns motivation, methodology, and experimental results across related papers to reconstruct research development chains. This task introduces key challenges, including temporally aligning loosely structured methods and standardizing heterogeneous experimental tables. We present ResearchPulse, an agent-based framework that integrates instruction planning, scientific content extraction, and structured visualization. It consists of three coordinated agents: a Plan Agent for task decomposition, a Mmap-Agent that constructs motivation-method mind maps, and a Lchart-Agent that synthesizes experimental line charts. To support this task, we introduce ResearchPulse-Bench, a citation-aware benchmark of annotated paper clusters. Experiments show that our system, despite using 7B-scale agents, consistently outperforms strong baselines like GPT-4o in semantic alignment, structural consistency, and visual fidelity. The dataset are available in https://huggingface.co/datasets/ResearchPulse/ResearchPulse-Bench